Publications related to Towards more Practical Threat Models in Artificial Intelligence Security

Voices from the Frontline: Revealing the AI Practitioners' viewpoint on the European AI Act

Artificial intelligence (AI) is increasingly used in an ever larger number of industries. Alongside this development, however, abundant works argue that AI-driven systems are lacking in terms of safety, ethics and transparency. As a direct consequence, the ...

2024

Exploring High-Performance and Energy-Efficient Architectures for Edge AI-Enabled Applications

Joshua Alexander Harrison Klein

The desire and ability to place AI-enabled applications on the edge has grown significantly in recent years. However, the compute-, area-, and power-constrained nature of edge devices are stressed by the needs of the AI-enabled applications, due to a gener ...

EPFL2024

Assessment framework for deepfake detection in real-world situations

Touradj Ebrahimi, Yuhang Lu

Detecting digital face manipulation in images and video has attracted extensive attention due to the potential risk to public trust. To counteract the malicious usage of such techniques, deep learning-based deepfake detection methods have been employed and ...

2024

When Your AI Becomes a Target: AI Security Incidents and Best Practices

Alexandre Massoud Alahi, Kathrin Grosse

In contrast to vast academic efforts to study AI security, few real-world reports of AI security incidents exist. Released incidents prevent a thorough investigation of the attackers' motives, as crucial information about the company and AI application is ...

AAAI Press2024

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

Sabine Süsstrunk, Alessio Verardo, Yufan Ren, Peter Arpad Grönquist, Qingyi He

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person’s expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Som ...

2024

The Current State of the OBI DICT Project: A Bilingual e-Dictionary of Oracle-Bone Inscriptions with AI Image Recognition

This article reports on the current state of the OBI DICT project, a bilingual e-dictionary of oracle-bone inscriptions (OBI), incorporating artificial intelligence (AI) image recognition technology. It first provides a brief overview of the development of ...

Buro Van Die Wat2024

Comparing various AI approaches to traditional quantitative assessment of the myocardial perfusion in [82Rb] PET for MACE prediction

Adrien Raphaël Depeursinge, Julien René Pierre Fageot, Daniel Abler

Assessing the individual risk of Major Adverse Cardiac Events (MACE) is of major importance as cardiovascular diseases remain the leading cause of death worldwide. Quantitative Myocardial Perfusion Imaging (MPI) parameters such as stress Myocardial Blood F ...

Nature Portfolio2024

EdgeAI-Aware Design of In-Memory Computing Architectures

Marco Antonio Rios

Driven by the demand for real-time processing and the need to minimize latency in AI algorithms, edge computing has experienced remarkable progress. Decision-making AI applications stand out for their heavy reliance on data-centric operations, predominantl ...

EPFL2024

Trusting the Explainers: Teacher Validation of Explainable Artificial Intelligence for Course Design

Tanja Christina Käser Jacober, Vinitra Swamy, Mirko Marras, Sijia Du

Deep learning models for learning analytics have become increasingly popular over the last few years; however, these approaches are still not widely adopted in real-world settings, likely due to a lack of trust and transparency. In this paper, we tackle th ...

2023

Robust Training and Verification of Deep Neural Networks

Fabian Ricardo Latorre Gomez

According to the proposed Artificial Intelligence Act by the European Comission (expected to pass at the end of 2023), the class of High-Risk AI Systems (Title III) comprises several important applications of Deep Learning like autonomous driving vehicles ...

EPFL2023

Exploiting Explanations to Detect Misclassifications of Deep Learning Models in Power Grid Visual Inspection

Olga Fink, Giovanni Floreale

In the context of automatic visual inspection of infrastructures by drones, Deep Learning (DL) models are used to automatically process images for fault diagnostics. While explainable Artificial Intelligence (AI) algorithms can provide explanations to asse ...

Research Publishing2023

Playing Brains: The Ethical Challenges Posed by Silicon Sentience and Hybrid Intelligence in DishBrain

The convergence of human and artificial intelligence is currently receiving considerable scholarly attention. Much debate about the resulting Hybrid Minds focuses on the integration of artificial intelligence into the human brain through intelligent brain- ...

2023

A multimodal measurement of the impact of deepfakes on the ethical reasoning and affective reactions of students

Touradj Ebrahimi, Patrick Jermann, Roland John Tormey, Cécile Hardebolle, Vivek Ramachandran, Nihat Kotluk

Deepfakes - synthetic videos generated by machine learning models - are becoming increasingly sophisticated. While they have several positive use cases, their potential for harm is also high. Deepfake production involves input from multiple engineers, maki ...

2023

The future of human-centric eXplainable Artificial Intelligence (XAI) is not post-hoc explanations

Tanja Christina Käser Jacober, Vinitra Swamy, Jibril Albachir Frej

Explainable Artificial Intelligence (XAI) plays a crucial role in enabling human understanding and trust in deep learning systems, often defined as determining which features are most important to a model's prediction. As models get larger, more ubiquitous ...

2023

Out of their minds? Externalist challenges for using AI in forensic psychiatry

Marcello Ienca, Ambra D'imperio

Harnessing the power of machine learning (ML) and other Artificial Intelligence (AI) techniques promises substantial improvements across forensic psychiatry, supposedly offering more objective evaluations and predictions. However, AI-based predictions abou ...

FRONTIERS MEDIA SA2023

Impact of Video Processing Operations in Deepfake Detection

Touradj Ebrahimi, Yuhang Lu

The detection of digital face manipulation in video has attracted extensive attention due to the increased risk to public trust. To counteract the malicious usage of such techniques, deep learning-based deepfake detection methods have been developed and ha ...

2023

A Virtual Simulation-Pilot Agent for Training of Air Traffic Controllers

Petr Motlicek, Amrutha Prasad, Juan Pablo Zuluaga Gomez

In this paper we propose a novel virtual simulation-pilot engine for speeding up air traffic controller (ATCo) training by integrating different state-of-the-art artificial intelligence (AI)-based tools. The virtual simulation-pilot engine receives spoken ...

MDPI2023

The Metaverse as a Virtual Model of Platform Urbanism: Its Converging AIoT, XReality, Neurotech, and Nanobiotech and Their Applications, Challenges, and Risks

Simon Elias Bibri

With their exponentially rising computational power, digital platforms are heralding a new era of hybrid intelligence. There has recently been much enthusiasm and hype that the Metaverse has the potential to unlock hybrid intelligence. This is premised on ...

MDPI2023

Probabilistic methods for neural combinatorial optimization

Nikolaos Karalias

The monumental progress in the development of machine learning models has led to a plethora of applications with transformative effects in engineering and science. This has also turned the attention of the research community towards the pursuit of construc ...

EPFL2023

BLACK-BOX ATTACKS ON IMAGE ACTIVITY PREDICTION AND ITS NATURAL LANGUAGE EXPLANATIONS

Andrea Cavallaro

Explainable AI (XAI) methods aim to describe the decision process of deep neural networks. Early XAI methods produced visual explanations, whereas more recent techniques generate multimodal explanations that include textual information and visual represent ...

Ieee Computer Soc2023